{"uid":"cap_xjVyDL0_1bUk-19l5IQxP","slug":"agentrxi-speech-to-text-transcription-whisper-large-v3-turbo-dcab663a","name":"AgentRXI Speech-to-Text Transcription (Whisper Large v3 Turbo)","description":"Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles. Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/transcribe?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string","description":"Public URL of an audio or video file (mp3, wav, m4a, ogg, webm, mp4)"},"language":{"type":"string","description":"Optional ISO 639-1 hint, e.g. en"},"audio_base64":{"type":"string","description":"Alternative to url: base64 audio bytes"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.011","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.011/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.011","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.011","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_t1_Mtece07tWsMa1Rm-qi","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.011","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio or video files via Whisper large v3 turbo, returning transcript text, detected language, timed segments, and WebVTT subtitles from a public URL or base64-encoded audio.","exampleAgentPrompt":"Can you transcribe this podcast episode for me? The audio file is at https://example.com/episode42.mp3 — I need the full transcript, the timed segments, and WebVTT subtitles.","exampleUseCases":[{"title":"Podcast episode transcription","prompt":"Transcribe this podcast episode at https://media.example.com/podcast/ep10.mp3 and give me the full text transcript along with the timed segments so I can find specific parts easily."},{"title":"Foreign-language video captioning","prompt":"I have a Spanish video at https://cdn.example.com/interview.mp4 — can you transcribe it and generate WebVTT subtitles? Pass 'es' as the language hint so it detects properly."},{"title":"Interview recording to text","prompt":"I recorded an interview and uploaded it here: https://storage.example.com/interview_audio.wav — please transcribe it and tell me what language was spoken, along with timestamped segments."}],"resultDescription":"Returns a transcript of the spoken content, the auto-detected language code, a list of timed segments (each with start/end timestamps and text), and a WebVTT subtitle file — all derived from the submitted audio or video source.","failureModes":["Audio/video URL is not publicly accessible (returns error)","File exceeds 20 MB size limit","Audio format not supported (only mp3, wav, m4a, ogg, webm, mp4 are accepted)","max_minutes cap exceeded leading to truncated transcript","Poor audio quality resulting in inaccurate transcription","Invalid base64 encoding if using audio_base64 input","Network timeout fetching remote URL"],"whenToPreferThis":"Choose this endpoint when you need fast, high-quality transcription with timed segments and WebVTT subtitle output in a single call, especially for pay-per-use scenarios via x402 micropayment without managing API keys. Ideal for agents handling public media URLs or base64 audio up to 20 MB with per-minute pricing and support for up to 30 minutes of audio.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:38:39.280Z","isFirstParty":false,"canonicalSlug":"agentrxi-speech-to-text-transcription-whisper-large-v3-turbo-dcab663a"}